Archive \ Volume.17 2026 Issue 1

Continual Learning without Silent Change in Medication-Support Systems

, , ,
  1. Department of Continual Learning and Medication Safety, College of Pharmacy, Kyung Hee University, Seoul, South Korea.
  2. Department of AI Stability in Pharmacy Systems, College of Pharmacy, Chung-Ang University, Seoul, South Korea.
  3. Department of Non-Silent AI Updates, College of Pharmacy, Kangwon National University, Chuncheon, South Korea.

Abstract

Medication-support systems may change after implementation because patient populations, clinical practices, data pipelines, coding conventions, medicine knowledge, model parameters, interfaces, and user responses evolve. Such change becomes unsafe to govern when it is not visible, version-linked, investigated, or subjected to evidence proportionate to its possible consequences. This article develops a proposed continual-learning control architecture for medication-support systems. It distinguishes continual learning from automatic production updating and defines silent change as a potentially consequential alteration in data, semantics, model behaviour, workflow position, human use, or decision effects that occurs without a contemporaneous and accountable assessment of whether requalification is required. The proposed architecture separates a locked operational plane from an isolated candidate-learning plane. Its principal components are an intended-use and change contract, multidimensional monitoring, change-event classification, an immutable version and evidence ledger, risk-proportionate requalification, staged release, rollback, suspension, and retirement. A no-silent-promotion boundary prevents a candidate version from replacing the operational version solely because retraining or automated updating has occurred. Evaluation must extend beyond discrimination to calibration, medication-task performance, workflow effects, human reliance, medication-safety signals, subgroup equity, traceability, and organizational readiness. Validation would require retrospective, external, prospective, human-factor, implementation, and post-release evidence matched to the system’s intended use and potential medication harm. The architecture does not establish clinical effectiveness, regulatory conformity, universal thresholds, or deployment readiness. Its original contribution is an integrated governance structure through which continual learning may remain technically possible while operational change remains visible, reviewable, reversible, and professionally accountable.


Downloads: 29
Views: 143

How to cite:
Vancouver
Kim D, Park J, Kang M, Jung H. Continual Learning without Silent Change in Medication-Support Systems. Arch Pharm Pract. 2026;17(1):57-67. https://doi.org/10.51847/65Q1PxmAOE
APA
Kim, D., Park, J., Kang, M., & Jung, H. (2026). Continual Learning without Silent Change in Medication-Support Systems. Archives of Pharmacy Practice, 17(1), 57-67. https://doi.org/10.51847/65Q1PxmAOE

Download Citation
References
  1. Kelly CJ, Karthikesalingam A, Suleyman M, Corrado G, King D. Key challenges for delivering clinical impact with artificial intelligence. BMC Med. 2019;17(1):195. doi:10.1186/s12916-019-1426-2
  2. Wiens J, Saria S, Sendak M, Ghassemi M, Liu VX, Doshi-Velez F, et al. Do no harm: A roadmap for responsible machine learning for health care. Nat Med. 2019;25(9):1337-40. doi:10.1038/s41591-019-0548-6
  3. Finlayson SG, Subbaswamy A, Singh K, Bowers J, Kupke A, Zittrain J, et al. The clinician and dataset shift in artificial intelligence. N Engl J Med. 2021;385(3):283-6. doi:10.1056/NEJMc2104626
  4. Davis SE, Embí PJ, Matheny ME. Sustainable deployment of clinical prediction tools—a 360° approach to model maintenance. J Am Med Inform Assoc. 2024;31(5):1195-8. doi:10.1093/jamia/ocae036
  5. Embí PJ. Algorithmovigilance—advancing methods to analyze and monitor artificial intelligence-driven health care for effectiveness and equity. JAMA Netw Open. 2021;4(4). doi:10.1001/jamanetworkopen.2021.4622
  6. Sahiner B, Chen W, Samala RK, Petrick N. Data drift in medical machine learning: Implications and potential remedies. Br J Radiol. 2023;96(1150):20220878. doi:10.1259/bjr.20220878
  7. Duckworth C, Chmiel FP, Burns DK, Zlatev ZD, White NM, Daniels TWV, et al. Using explainable machine learning to characterise data drift and detect emergent health risks for emergency department admissions during COVID-19. Sci Rep. 2021;11(1):23017. doi:10.1038/s41598-021-02481-y
  8. Rahmani K, Thapa R, Tsou P, Chetty SC, Barnes G, Lam C, et al. Assessing the effects of data drift on the performance of machine learning models used in clinical sepsis prediction. Int J Med Inform. 2023;173:104930. doi:10.1016/j.ijmedinf.2022.104930
  9. Zech JR, Badgeley MA, Liu M, Costa AB, Titano JJ, Oermann EK. Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study. PLoS Med. 2018;15(11). doi:10.1371/journal.pmed.1002683
  10. Subbaswamy A, Saria S. From development to deployment: Dataset shift, causality, and shift-stable models in health AI. Biostatistics. 2020;21(2):345-52. doi:10.1093/biostatistics/kxz041
  11. Sendak MP, Ratliff W, Sarro D, Alderton E, Futoma J, Gao M, et al. Real-world integration of a sepsis deep learning technology into routine clinical care: Implementation study. JMIR Med Inform. 2020;8(7). doi:10.2196/15182
  12. Vollmer S, Mateen BA, Bohner G, Király FJ, Ghani R, Jonsson P, et al. Machine learning and artificial intelligence research for patient benefit: 20 critical questions on transparency, replicability, ethics, and effectiveness. BMJ. 2020;368. doi:10.1136/bmj.l6927
  13. Balendran A, Benchoufi M, Evgeniou T, Ravaud P. Algorithmovigilance, lessons from pharmacovigilance. NPJ Digit Med. 2024;7(1):270. doi:10.1038/s41746-024-01237-y
  14. Gebru T, Morgenstern J, Vecchione B, Vaughan JW, Wallach H, Daumé H III, et al. Datasheets for datasets. Commun ACM. 2021;64(12):86-92. doi:10.1145/3458723
  15. Lehne M, Sass J, Essenwanger A, Schepers J, Thun S. Why digital medicine depends on interoperability. NPJ Digit Med. 2019;2:79. doi:10.1038/s41746-019-0158-1
  16. Davis SE, Greevy RA Jr, Lasko TA, Walsh CG, Matheny ME. Detection of calibration drift in clinical prediction models to inform model updating. J Biomed Inform. 2020;112:103611. doi:10.1016/j.jbi.2020.103611
  17. Kore A, Abbasi Bavil E, Subasri V, Abdalla M, Fine B, Dolatabadi E, et al. Empirical data drift detection experiments on real-world medical imaging data. Nat Commun. 2024;15(1):1887. doi:10.1038/s41467-024-46142-w
  18. Norgeot B, Quer G, Beaulieu-Jones BK, Torkamani A, Dias R, Gianfrancesco M, et al. Minimum information about clinical artificial intelligence modeling: The MI-CLAIM checklist. Nat Med. 2020;26(9):1320-4. doi:10.1038/s41591-020-1041-y
  19. Collins GS, Moons KGM, Dhiman P, Riley RD, Beam AL, Van Calster B, et al. TRIPOD+AI statement: Updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ. 2024;385. doi:10.1136/bmj-2023-078378
  20. Subasri V, Krishnan A, Kore A, Dhalla A, Pandya D, Wang B, et al. Detecting and remediating harmful data shifts for the responsible deployment of clinical AI models. JAMA Netw Open. 2025;8(6). doi:10.1001/jamanetworkopen.2025.13685
  21. Vasey B, Nagendran M, Campbell B, Clifton DA, Collins GS, Denaxas S, et al. Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI. Nat Med. 2022;28(5):924-33. doi:10.1038/s41591-022-01772-9
  22. Liu X, Cruz Rivera S, Moher D, Calvert MJ, Denniston AK, SPIRIT-AI and CONSORT-AI Working Group. Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: The CONSORT-AI extension. Nat Med. 2020;26(9):1364-74. doi:10.1038/s41591-020-1034-x
  23. Lacson R, Eskian M, Licaros A, Kapoor N, Khorasani R. Machine learning model drift: A systematic review. J Am Coll Radiol. 2022;19(10):1162-9. doi:10.1016/j.jacr.2022.05.030
  24. Nagendran M, Chen Y, Lovejoy CA, Gordon AC, Komorowski M, Harvey H, et al. Artificial intelligence versus clinicians: Systematic review of design, reporting standards, and claims of deep learning studies. BMJ. 2020;368. doi:10.1136/bmj.m689
  25. Lekadir K, Frangi AF, Porras AR, Glocker B, Cintas C, Langlotz CP, et al. FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare. BMJ. 2025;388. doi:10.1136/bmj-2024-081554
  26. Graafsma J, Murphy RM, van de Garde EMW, Karapinar-Çarkit F, Derijks HJ, Hoge RHL, et al. The use of artificial intelligence to optimize medication alerts generated by clinical decision support systems: A scoping review. J Am Med Inform Assoc. 2024;31(6):1411-22. doi:10.1093/jamia/ocae076
  27. Corny J, Rajkumar A, Martin O, Dode X, Lajonchère JP, Billuart O. A machine learning-based clinical decision support system to identify prescriptions with a high risk of medication error. J Am Med Inform Assoc. 2020;27(11):1688-94. doi:10.1093/jamia/ocaa154
  28. Strohm L, Hehakaya C, Ranschaert ER, Boon WPC, Moors EHM. Implementation of artificial intelligence applications in radiology: Hindering and facilitating factors. Eur Radiol. 2020;30(10):5525-32. doi:10.1007/s00330-020-06946-y
  29. Gaube S, Suresh H, Raue M, Merritt A, Berkowitz SJ, Lermer E, et al. Do as AI say: Susceptibility in deployment of clinical decision-aids. NPJ Digit Med. 2021;4(1):31. doi:10.1038/s41746-021-00385-9
  30. Daye D, Wiggins WF, Lungren MP, Alkasab TK, Kottler N, Allen B Jr, et al. Implementation of clinical artificial intelligence in radiology: Who decides and how? Radiology. 2022;305(3):555-63. doi:10.1148/radiol.212151
  31. Bate A, Hobbiger SF. Artificial intelligence, real-world automation and the safety of medicines. Drug Saf. 2021;44(2):125-32. doi:10.1007/s40264-020-01001-7
  32. Obermeyer Z, Powers B, Vogeli C, Mullainathan S. Dissecting racial bias in an algorithm used to manage the health of populations. Science. 2019;366(6464):447-53. doi:10.1126/science.aax2342
  33. Gianfrancesco MA, Tamang S, Yazdany J, Schmajuk G. Potential biases in machine learning algorithms using electronic health record data. JAMA Intern Med. 2018;178(11):1544-7. doi:10.1001/jamainternmed.2018.3763
  34. Rajkomar A, Hardt M, Howell MD, Corrado G, Chin MH. Ensuring fairness in machine learning to advance health equity. Ann Intern Med. 2018;169(12):866-72. doi:10.7326/M18-1990
  35. McCradden MD, Joshi S, Mazwi M, Anderson JA. Ethical limitations of algorithmic fairness solutions in health care machine learning. Lancet Digit Health. 2020;2(5). doi:10.1016/S2589-7500(20)30065-

 

 


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.